Leader360V: A Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment

This makes 360 scene understanding tasks,, segmentation and tracking, crucial for appications, such as autonomous driving, robotics. With the recent emergence of foundation models, the community is, however, impeded by the lack of large-scale, labelled real-world datasets. This is caused by the inherent spherical properties,, severe distortion in polar regions, and content discontinuities, rendering the annotation costly yet complex.